In the context of unknown inputs (unknown dynamic biases) and unknown measurement systematic errors, this article studies the extension of robust three-stage Kalman filter (ERThSKF) that satisfies high precision entry navigation filter requirements for Mars pinpoint landing mission. The imprecise dynamic model with uncertain parameters could produce unknown inputs. Using radiometric beacons and/or inertial measurement unit (IMU) as output observation during the Mars atmospheric entry phase, the measurement data from the radio range and/or IMU have unknown measurement systematic errors. To solve these problems, we made an ERThSKF to obtain the accurate state estimation of the uncertain non-linear Mars system with unknown inputs and unknown measurement systematic errors which can be effectively estimated and compensated. Computer simulations show that the proposed navigation filter algorithm in this study can achieve high convergence speed and minor errors, which fulfils the need of future pinpoint Mars landing missions.
This paper proposed a two-stage robust extended Kalman filter (TREKF) for state estimation of non-linear uncertain system with unknown inputs. In engineering practice, the extended Kalman filter (EKF) with unknown inputs of the non-linear uncertain system may be degraded or even diverged. The optimal two-stage EKF (TEKF) is designed to solve the unknown inputs. The robust EKF (REKF) is considered to solve the non-linear uncertain system for a long time. However, the information about the non-linear uncertain system with unknown inputs is always incorrect. To solve this problem, the TREKF is designed by using the advantages of the TEKF and REKF, furthermore, its stability is proved. Finally, the performances of the TREKF, which are compared with the results of the REKF, TEKF and EKF, are verified by illustrating a numerical example of the powered descent phase of Mars EDL (entry, descent and landing). These also verify that the unfavourable effects of the model uncertainties and the unknown inputs are reduced efficiently by using the TREKF for the miniature coherent altimeter and velocimeter and inertial measurement unit integrated navigation during the powered descent phase of Mars EDL.
Prescription dispensing accuracy is of paramount importance for all hospitals. However, human errors are inevitable due to multiple reasons, such as fatigue, stress, heavy workload, lack of effective verification measures, mismanagement. Such human errors pose serious safety and health concerns on the part of patients and may as well lead to a series of medical disputes. Based on induced deep learning, this paper proposes a real-time Blister Package Identification System (BPIS) to assist pharmacists' drug verification and dispensing. Under the guidance of the induction strategy, image preprocessing is introduced to form a standardized image containing the front and back side of the blister package, which is subsequently sent to CNN-based object identification network for feature extraction and identification. This preprocessing method allows the identification system to promote the deep learning system to focus on feature learning to obtain more information about the appearance of the package ruling out confounding factors such as background noise, size, shape or positioning. In addition, this article collects and establishes an image dataset of adult lozenges. Under this dataset, this paper verifies the enhancement of Induced Deep Learning (IDL) on YOLO v2, ResNet, and SENet. By optimizing the deep learning identification network with the help of the embedded technology and a two-side extraction mechanism, a real-time BPIS is built. Long-term tests in hospitals prove the effectiveness of the proposed system.INDEX TERMS Blister package identification, deep learning, induction, dispensing error, CNN.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.